Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Diving into new experiences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Clever
    -0.09
    shof
    -0.08
     Mannheim
    -0.08
     України
    -0.07
    assembl
    -0.07
    wera
    -0.07
     अनुम
    -0.07
     नियंत्र
    -0.07
     predictions
    -0.07
     अनुमान
    -0.07
    POSITIVE LOGITS
     vào
    0.11
     dive
    0.11
    深
    0.10
     深
    0.10
    深入
    0.10
     깊
    0.10
     depths
    0.10
     deeper
    0.10
     plonge
    0.10
     sâu
    0.09
    Act Density 0.024%

    No Known Activations